search

martianxiu / MSECNet

This is the official implementation of our paper MSECNet: Accurate and Robust Normal Estimation for 3D Point Clouds by Multi-Scale Edge Conditioning (ACMMM2023)
Other
23 stars 1 forks source link

File of point index #1

Closed anonymouslosty closed 1 year ago

anonymouslosty commented 1 year ago

Hello! Thanks for your great work! When I try to test the accuracy of the inference, I found that line 416 in test_sparse_full_PCPNet.py which require file of the format ".pidx.npy". I ran the download_pclouds.py and I did not get the file matched that format, only ".pidx" existed. I wonderer whether I should convert the format of ".pidx" file into ".pidx.npy" manually or the format changed itself when I ran the code. Best.

anonymouslosty commented 1 year ago

I found the code in PCPNet dataset.py.

            patch_indices = np.loadtxt(pidx_filename).astype('int')
            np.save(pidx_filename+'.npy', patch_indices)

It works.